{"id":"W2171625237","doi":"10.1111/j.1745-3984.2007.00024.x","title":"An Investigation into the Dimensionality of TOEFL Using Conditional Covariance‐Based Nonparametric Approach","year":2007,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":82,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Test of English as a Foreign Language; Reading comprehension; Curse of dimensionality; Psychology; Covariance; Nonparametric statistics; Natural language processing; Computer science; Reading (process); Artificial intelligence; Statistics; Mathematics education; Mathematics; Linguistics; Language assessment","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04481614,0.0001217269,0.0003037101,0.0008840276,0.0002322329,0.00007878846,0.000685219,0.00006131805,0.0001734544],"category_scores_gemma":[0.04865053,0.00007390974,0.0001562452,0.002692367,0.0002159721,0.0003290494,0.0000260863,0.0002299741,0.000002538178],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003231888,"about_ca_system_score_gemma":0.001392651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007506497,"about_ca_topic_score_gemma":0.000005807261,"domain_scores_codex":[0.9928173,0.0008380974,0.001543714,0.0002350922,0.00438582,0.0001799354],"domain_scores_gemma":[0.9770635,0.01532736,0.002165742,0.0003874993,0.004859741,0.0001961962],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0004795206,0.00244027,0.7611208,0.00004385879,0.000240159,0.000002470654,0.002607666,0.1001654,0.0745033,0.03010797,0.003045087,0.02524352],"study_design_scores_gemma":[0.0004428792,0.0001648045,0.8532051,0.00004274281,0.00004001799,0.00003818879,0.001191709,0.005316137,0.003720192,0.1355324,0.000198944,0.0001068892],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7064911,0.0004805414,0.2904174,0.001305201,0.0008899372,0.0001309356,0.000003273301,0.000002229893,0.0002794167],"genre_scores_gemma":[0.7780539,0.000001269151,0.2212734,0.0003114999,0.0003443653,0.000001689126,0.000003203673,0.000004540766,0.000006103734],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1054244,"threshold_uncertainty_score":0.9835628,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6245000768597356,"score_gpt":0.5087043214551444,"score_spread":0.1157957554045912,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}